Update examples to use transcription events from context aggregators

examples/foundational/19-openai-realtime.py

@@ -15,14 +15,17 @@ from loguru import logger
 from pipecat.adapters.schemas.function_schema import FunctionSchema
 from pipecat.adapters.schemas.tools_schema import ToolsSchema
 from pipecat.audio.vad.silero import SileroVADAnalyzer
-from pipecat.frames.frames import LLMRunFrame, LLMSetToolsFrame, TranscriptionMessage
+from pipecat.frames.frames import LLMRunFrame, LLMSetToolsFrame
 from pipecat.observers.loggers.transcription_log_observer import TranscriptionLogObserver
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
 from pipecat.processors.aggregators.llm_context import LLMContext
-from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
-from pipecat.processors.transcript_processor import TranscriptProcessor
+from pipecat.processors.aggregators.llm_response_universal import (
+    AssistantTurnStoppedMessage,
+    LLMContextAggregatorPair,
+    UserTurnStoppedMessage,
+)
 from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport
 from pipecat.services.llm_service import FunctionCallParams
@@ -177,8 +180,6 @@ Remember, your responses should be short. Just one or two sentences, usually. Re
     llm.register_function("get_restaurant_recommendation", fetch_restaurant_recommendation)
     llm.register_function("get_news", get_news)
 
-    transcript = TranscriptProcessor()
-
     # Create a standard OpenAI LLM context object using the normal messages format. The
     # OpenAIRealtimeLLMService will convert this internally to messages that the
     # openai WebSocket API can understand.
@@ -189,15 +190,16 @@ Remember, your responses should be short. Just one or two sentences, usually. Re
 
     context_aggregator = LLMContextAggregatorPair(context)
 
+    user_aggregator = context_aggregator.user()
+    assistant_aggregator = context_aggregator.assistant()
+
     pipeline = Pipeline(
         [
             transport.input(),  # Transport user input
-            context_aggregator.user(),
-            transcript.user(),  # LLM pushes TranscriptionFrames upstream
+            user_aggregator,
             llm,  # LLM
             transport.output(),  # Transport bot output
-            transcript.assistant(),  # After the transcript output, to time with the audio output
-            context_aggregator.assistant(),
+            assistant_aggregator,
         ]
     )
 
@@ -238,14 +240,18 @@ Remember, your responses should be short. Just one or two sentences, usually. Re
         logger.info(f"Client disconnected")
         await task.cancel()
 
-    # Register event handler for transcript updates
-    @transcript.event_handler("on_transcript_update")
-    async def on_transcript_update(processor, frame):
-        for msg in frame.messages:
-            if isinstance(msg, TranscriptionMessage):
-                timestamp = f"[{msg.timestamp}] " if msg.timestamp else ""
-                line = f"{timestamp}{msg.role}: {msg.content}"
-                logger.info(f"Transcript: {line}")
+    # Log transcript updates
+    @user_aggregator.event_handler("on_user_turn_stopped")
+    async def on_user_turn_stopped(aggregator, strategy, message: UserTurnStoppedMessage):
+        timestamp = f"[{message.timestamp}] " if message.timestamp else ""
+        line = f"{timestamp}user: {message.content}"
+        logger.info(f"Transcript: {line}")
+
+    @assistant_aggregator.event_handler("on_assistant_turn_stopped")
+    async def on_assistant_turn_stopped(aggregator, message: AssistantTurnStoppedMessage):
+        timestamp = f"[{message.timestamp}] " if message.timestamp else ""
+        line = f"{timestamp}assistant: {message.content}"
+        logger.info(f"Transcript: {line}")
 
     runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)